> For the complete documentation index, see [llms.txt](https://quandora.gitbook.io/quandora-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://quandora.gitbook.io/quandora-docs/getting-started/quickstart.md).

# Quickstart

The goal: connect Quandora to your AI agent, run one research task, and read an evidence-backed factor report.

### Who This Is For

Solo systematic traders, AI power users, and market-curious builders who already use tools like Claude Code, Codex, or OpenClaw — and want their agent to work from market evidence instead of guesses.

### Before You Start

* An agent host: Claude Code, Codex, or OpenClaw
* A Quandora account — authorization happens in your browser
* 10–15 minutes
* No exchange API key — the first research workflow doesn't touch trading. Authorization is browser OAuth only.

### 1. Install And Connect

Follow the [Installation Guide](/quandora-docs/getting-started/installation-guide.md) for your host. Claude Code example:

```
claude plugin marketplace add varsity-tech-product/quandora-plugins
claude plugin install quandora@quandora
```

Then open `/mcp`, authenticate `quandora`, and start a new chat.

### 2. Run Your First Task

List the public research tasks:

```
/factor-mining show public tasks
```

Pick one, or let the agent choose:

```
Use Quandora Factor Mining to pick a public research task, generate a factor,
run the backtest, and give me a plain-English verdict with key metrics and risks.
```

Your agent will read the [task card](/quandora-docs/understanding-quandora/task-card.md), check memory for duplicates, write [`plugin.py`](/quandora-docs/understanding-quandora/plugin.py.md), and submit it. Quandora binds market data server-side and runs the backtest — mining typically takes a few minutes.

### 3. Read Your Result

The run returns a [factor card](/quandora-docs/understanding-quandora/factor-card.md) — verdict first, then evidence, risks, and a suggested next experiment — plus charts and result files saved to your workspace:

See [How Factors Are Judged](/quandora-docs/understanding-quandora/how-factors-are-judged.md) to understand why your factor passed or failed.

### You're Done When

Your agent ran one Quandora research task and returned a report you can understand.

A rejected verdict still counts — rejections become memory and sharpen the next attempt.

{% hint style="info" %}
Factor mining tests ideas — it does not place trades. Execution comes later in the workflow: your strategy, paper-verified first, under your risk limits and kill switch. A factor card is evidence about the past, not a promise about the future.
{% endhint %}

### Next Steps

* Browse the [research task families](/quandora-docs/understanding-quandora/research-tasks.md)
* See what data your agent can use in [Our Data](/quandora-docs/understanding-quandora/our-data.md)
* New to the jargon? Keep the [Glossary](/quandora-docs/understanding-quandora/glossary.md) open


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://quandora.gitbook.io/quandora-docs/getting-started/quickstart.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.